Joined June 2013
78 Photos and videos
Pinned Tweet
15 Feb 2021
Nuevo vídeo! Siguiendo con la serie de creando videojuegos, os traigo Shipped de Alva Majo (@5ro4) pero en 3D ! 😏 Para ver que tal ha quedado, dejo el vídeo por aquí! youtu.be/bMq3-IjOZU0 #gamedev #devsfromspain #indiedev #unity #unity3d #indiesp
15
37
268
JLPM retweeted
Have you ever wondered if we could capture human movement without mocap suits, VR trackers, or camera setups? What if all you needed was a pair of everyday insoles? 👟 Introducing Step2Motion, accepted to #Eurographics2026! 📝Project Page: vcai.mpi-inf.mpg.de/projects… 🧵👇
10
32
251
17,836
JLPM retweeted
25 Oct 2023
"Motion Matching implementation for Unity" github.com/JLPM22/MotionMatc…
16
75
6,914
JLPM retweeted
📈 The Steam Dev Cheat Sheet 🏆 A dense collection of best practices, magic formulas, and Steam knowledge to help #indiedev folks like me. 📺 PLUS a 5:40 video briefly covering each section. Links to everything below: 🧵
20
553
3,306
263,958
JLPM retweeted
2 Jun 2023
Example-based Motion Synthesis via Generative Motion Matching paper page: huggingface.co/papers/2306.0… present GenMM, a generative model that "mines" as many diverse motions as possible from a single or few example sequences. In stark contrast to existing data-driven methods, which typically require long offline training time, are prone to visual artifacts, and tend to fail on large and complex skeletons, GenMM inherits the training-free nature and the superior quality of the well-known Motion Matching method. GenMM can synthesize a high-quality motion within a fraction of a second, even with highly complex and large skeletal structures. At the heart of our generative framework lies the generative motion matching module, which utilizes the bidirectional visual similarity as a generative cost function to motion matching, and operates in a multi-stage framework to progressively refine a random guess using exemplar motion matches. In addition to diverse motion generation, we show the versatility of our generative framework by extending it to a number of scenarios that are not possible with motion matching alone, including motion completion, key frame-guided generation, infinite looping, and motion reassembly.
6
34
161
93,705
JLPM canal de @JLPMdev or cierto, no me abre en pestaña incógnito y está bugueado... Está inactivo desde hace casi un año pero tiene unos vídeos muy "curradoos" Link: youtube.com/@JLPM/videos
1
2
4
680
JLPM retweeted
21 Mar 2023
Have been asked a few questions about the new VIVE self tracking tracker, so here's a thread 🧵! We're announcing it at GDC as a developer preview, with launch later in Q3. It's fully self tracking, so doesn't need external sensors or a headset to see it. 👀 (1/x)
40
177
1,065
254,125
JLPM retweeted
5
249
2,097
58,952
JLPM retweeted
Tiny changes to the order in which you update positions x and velocities v can be the difference between your simulation blowing up or dying down. But for many systems, *symplectic* integrators guarantee energy is preserved forever. Full lecture here: youtube.com/watch?v=Fi9xu3z9…
24
389
2,381
JLPM retweeted
10 Dec 2022
Git visual, worth a thousand words
98
2,006
11,306
JLPM retweeted
"So if you need to rotate something with grace, Quaternions will help you find the right place." #ChatGPT @JLPMdev
1
1
JLPM retweeted
the four most common 3D rotation representations
32
504
3,468
10 Oct 2022
He sido seleccionado para la beca de doctorado FPU!!! Ahora tengo financiación para seguir investigando en Realidad Virtual y Computer Animation :))
🔴 Publicada la resolución provisional de selección en segunda fase de las ayudas para formación de profesorado universitario (FPU) 2021. 🔗 universidades.gob.es/portal/…
4
21
JLPM retweeted
Vox Cleaner V2, My Blender add-on is Out now, for Free! Enjoy!
17
53
364
JLPM retweeted
This paper shows some of our research at Meta Reality Labs in reconstructing a user's pose from only the sensors of the Quest headset using Reinforcement Learning. authors: with Jungdam Won and Yuting Ye paper: arxiv.org/abs/2209.09391 video: youtu.be/CkTHsz6Ldas 1/4👇
52
595
3,107
JLPM retweeted
My "How to ML Paper - A brief Guide" (docs.google.com/document/d/1…) is getting visitors again! Good luck with your #ICLR2023 submissions :)
5
82
618
JLPM retweeted
My latest blog post is on how we can automatically create looping animations from motion capture data: theorangeduck.com/page/creat… Web demo here: theorangeduck.com/media/uplo…
3
38
158
20 Sep 2022
It was great to participate at ACM SIGGRAPH/Eurographics #SCA2022 with our paper "Combining Motion Matching and Orientation Prediction to Animate Avatars for Consumer-Grade VR Devices" We present a method to animate VR avatars with Motion Matching! 🧵 upc-virvig.github.io/MMVR/
1
4
24
20 Sep 2022
To obtain accurate positioning of the hands, we apply inverse kinematics with the hand-held controllers as end effectors
1
20 Sep 2022
Code, data and the paper are available on the project website! upc-virvig.github.io/MMVR/ Thanks @SympCompAnim for organizing a great conference! and my colleagues @ClipeCurie and supervisors for all the support :)
1
4